Source proof for Zalando Builds a GPT-4o Content Creation Copilot to Auto-Suggest Product Attributes

…. First, we stopped generating suggestions for some unsupported attribute sets. Second, we migrated to GPT-4o model, which significantly lowered costs. A further challenge involved identifying the optimal set of images to enhance i…

…proved, but we chose the part of the highest impact on the customer experience: generating attributes based on provided images. However, this presented our first challenge: with so many solutions on the mar…

…es, we've been consistently identifying opportunities to reduce error rates. As the manual process contributed to approximately 25% of the overall content production timeline, we've prioritized the development of assistive functions to support the QA pro…

…and the content creation experts are now actively contributing to the prompts. We've achieved an accuracy rate of approximately 75%, and we're enriching around 50,000 attributes on average per week. As a next step, we will focus on improving accuracy for niche categories and ex…

…ted on Sep 18, 2024 Tags: LLM , Machine Learning , UI , Frontend Introduction ¶ At Zalando, we strive to discover valuable use cases that benefit our customers and stakeholders by using AI-based approaches. Our team's primary mission is to enable content creation teams to produce and i…

…ce (QA) themselves to guarantee the four-eyes principle. After QA is completed, the article is published in the shop. The enriched attributes are then available to Zalando customers across Europe,…

…e content creation stage of the product onboarding is largely a manual process. Copywriters enrich attributes using a Content Creation Tool and perform Quality Assurance (QA) themselves to guarantee the four-eyes principle. After QA is completed, the article is published in the shop. The enriched attri…

…es, we've been consistently identifying opportunities to reduce error rates. As the manual process contributed to approximately 25% of the overall content production timeline, we've prioritized the development of assistive functions to support the QA pro…

…r content. Our system is designed to combine AI input with other sources, while the user interface clearly shows what suggestions come from which source, leaving the final decision in the hands of the human. This approach not only improves quality but also speeds up Time to Online (TTO…

…imperative for us to ensure the output of OpenAI was compatible with our APIs. We built a translation layer that converts OpenAI output into information directly usable by Zalando and discards the part that is not relevant. Another challenge was that some attributes shouldn't be filled for certain type…

…and the content creation experts are now actively contributing to the prompts. We've achieved an accuracy rate of approximately 75%, and we're enriching around 50,000 attributes on average per week. As a next step, we will focus on improving accuracy for niche categories and ex…

…s come from which source, leaving the final decision in the hands of the human. This approach not only improves quality but also speeds up Time to Online (TTO), allowing Zalando customers to gain access to more new products daily and enjoy…

…mpts based on the attributes and attribute sets coming from Article Masterdata. The prompts and image URLs are sent to OpenAI-GPT for further processing. OpenAI-GPT : Processes the prompts received from the Prompt Generator and provi…

…reviewed by domain experts. After doing a thorough analysis and multiple tests, we decided to use the OpenAI GPT-4 Turbo model, as it provided the right balance between accuracy and information coverage. We…

…. First, we stopped generating suggestions for some unsupported attribute sets. Second, we migrated to GPT-4o model, which significantly lowered costs. A further challenge involved identifying the optimal set of images to enhance i…

…and the content creation experts are now actively contributing to the prompts. We've achieved an accuracy rate of approximately 75%, and we're enriching around 50,000 attributes on average per week. As a next st…

…ot, like the ones used in IDEs for developers, to make life easier for users by automating parts of the article enrichment process. By leveraging Machine Learning, we streamline the task of adding attributes to…